Dimitry Gorinevsky
Papers
5
Total Citations
94
H-Index
4
About
Dimitry Gorinevsky is a pioneering researcher in the field of intelligent control systems, with a primary focus on model-free feedforward control, nonlinear approximation, and robotic manipulator dynamics. His major contributions lie in developing novel paradigms for trajectory tracking that eliminate the need for complex mathematical models of robotic systems. Instead, Gorinevsky pioneered the use of learning procedures and databases to compute feedforward control, demonstrating that neural networks and radial basis function (RBF) networks can effectively approximate control dependencies on task parameters. His most cited work (41 citations) introduced a groundbreaking model-free approach for direct-drive manipulator tracking, experimentally validating that nonlinear approximations could replace traditional model-based controllers. Across his career, Gorinevsky's research has accumulated over 94 citations, with notable experimental implementations in direct-drive and flexible manipulator systems. His work on comparing neural network-like methods for inverse kinematics approximation (1993) provided early insights into the practical application of artificial neural networks in robotics. Gorinevsky's achievements include establishing a new paradigm for feedforward control that remains influential in modern robotics and control theory, particularly for systems where accurate mathematical models are difficult to obtain.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5